SShogo Bench

Claude Fable 5.2 vs Claude Sonnet 5

Claude Fable 5.2 leads Claude Sonnet 5 by 24.0 points on the Shogo Agent Index. Claude Fable 5.2 wins 15 and Claude Sonnet 5 wins 0 of 15 shared benchmarks. Claude Sonnet 5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Claude Sonnet 5
Agentic coding8657
Long-horizon autonomy7865
Knowledge-work agents6743
Computer use7740
Security & context learning6551

Shared benchmarks

BenchmarkClaude Fable 5.2Claude Sonnet 5
APEX-Agentsindex80.1%54.5%
Vending-Bench 2index$9,628$6,378
CursorBenchindex60.0%34.1%
Chess Puzzles79.0%45.0%
CritPt35.7%16.9%
DTBench99.2%92.5%
FrontierMath Tier 4100.0%29.3%
FrontierMath Tiers 1-395.1%65.6%
GPQA Diamond96.0%90.5%
LMCA70.6%50.0%
OTIS Mock AIME99.7%94.7%
ProofBench100.0%77.0%
SciCode67.7%54.3%
SimpleBench94.9%60.6%
SimpleQA Verified94.0%33.7%

Specs and price

Claude Fable 5.2Claude Sonnet 5
Agent Index76.4 (#1)52.4 (#32)
Agent $/M$3.21$0.92
Input / output $/M$8.00 / $40.00$2.00 / $10.00
Context1M1M
ReleasedNov 9, 2026Jun 30, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and Claude Sonnet 5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo